Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed AI video prompt-building guide with no evidence of data access, persistence, or unsafe execution behavior.
Install this if you want a Chinese-oriented AI video prompt workflow. Review generated prompts before using them on external video platforms, and note that the bundled helper script appears incomplete, so the Markdown guidance is likely the usable part.
The skill hard-codes that prompts should be output only in Chinese, which can override or ignore a user's language preference and reduce transparency for users who cannot read Chinese. In a prompt-building skill, this is primarily a policy/usability control issue rather than a direct security exploit, but it can cause misunderstanding of generated content and downstream misuse.
Repeating a Chinese-only output requirement in the capability section reinforces behavior that may prevent users from receiving prompts in their preferred language. In this skill's context, the issue is somewhat less dangerous because it appears tied to optimization for a Chinese platform, but it still creates avoidable user-control and comprehension risks.
The document title and surrounding instructional content are presented in Chinese, which imposes a specific language on users without any visible opt-in or alternative language option. Under the policy criteria, a fixed language choice can be a natural-language policy concern when no user choice is offered.
This code primarily presents prompts and UI text in Chinese, but the embedded example strings force the English phrase "clinical light" in generated prompt content. Because the file does not offer a user language or locale choice for these prompt terms, it can be read as imposing a specific language style without opt-in.
No suspicious patterns detected.
